policies = pd.read_csv("data/motor/policies.csv",
    parse_dates=["inception_date", "expiry_date",
                 "cancellation_date"])
policies["inception_date"].dtype      # datetime64[us]

pd.to_datetime("2024-03-04")                  # 4 March
pd.to_datetime("03/04/2024")                  # 4 March (US)
pd.to_datetime("03/04/2024", dayfirst=True)   # 3 April (UK)

pd.to_datetime(["2024-03-04", "04/03/2024"])
# ValueError: time data "04/03/2024" doesn't match
#             format "%Y-%m-%d"

pd.to_datetime(["2024-02-30", "2024-03-01"],
               format="%Y-%m-%d", errors="coerce")
# [NaT, Timestamp('2024-03-01')]      NaT = "not a time"

d = pd.to_datetime(pd.Series(["2024-02-29", "2023-12-31"]))

d.dt.year            # [2024, 2023]
d.dt.month           # [2, 12]
d.dt.day_name()      # ['Thursday', 'Sunday']
d.dt.dayofyear       # [60, 365]
d.dt.is_leap_year    # [True, False]
d.dt.days_in_month   # [29, 31]

claims["accident_year"] = claims["accident_date"].dt.year
claims["report_lag"] = (claims["report_date"]
                        - claims["accident_date"]).dt.days

start = pd.Timestamp("2024-01-15")

start + pd.Timedelta(days=365)     # 2025-01-14  ← a day short!
start + pd.DateOffset(years=1)     # 2025-01-15  ← calendar-aware

pd.Timestamp("2024-02-29") + pd.DateOffset(years=1)
# 2025-02-28   (no 29 Feb in 2025)

gap = pd.Timestamp("2025-01-14") - start
gap                                 # Timedelta('365 days')
gap.days                            # 365
gap / pd.Timedelta(days=365.25)     # 0.999315...

def calendar_exposure(start, end, year):
    """Years of exposure earned in `year` by cover from start to end
    (inclusive). Each day weighs 1/365, or 1/366 in a leap year."""
    y0 = pd.Timestamp(f"{year}-01-01")
    y1 = pd.Timestamp(f"{year}-12-31")
    days = (end.clip(upper=y1) - start.clip(lower=y0)).dt.days + 1
    return days.clip(lower=0) / (366 if y1.is_leap_year else 365)


cy = pd.DataFrame({
    y: calendar_exposure(p["inception_date"], p["earned_end"], y)
    for y in range(2022, 2026)
})
p["exposure"] = cy.sum(axis=1)

term_days = (p["expiry_date"] - p["inception_date"]).dt.days + 1
year_days = pd.Series({y: 366 if pd.Timestamp(f"{y}-01-01").is_leap_year
                          else 365 for y in cy.columns})

# CY exposure × days-in-year → covered days in that year;
# ÷ term days → share of the term; × written premium
ep = (cy.mul(year_days, axis=1)
        .div(term_days, axis=0)
        .mul(p["written_premium"], axis=0))
ep.sum().round(0)
# 2022    4,418,313
# 2023    9,068,643
# 2024    9,614,807
# 2025    9,984,868

• I parse dates with an explicit format and count any NaTs
• I use .dt for properties and date differences
• I use DateOffset for calendar steps, Timedelta for durations
• I handle cancellations and the evaluation date with min and clip

• My calendar-split exposure totals 18,579.58 policy years
• I can explain CY, PY, and AY — and which pairs with which
• I earn premium on the same basis as exposure
• I computed claim frequency by accident year